Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to time or chronological order, particularly regarding the specific year mentioned

    oai_token-act-pair · gpt-3.5-turbo

    references to specific years and their significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     cumbers
    -0.66
     zipper
    -0.62
    cro
    -0.60
    ogle
    -0.59
    uits
    -0.59
     heartbeat
    -0.58
     textual
    -0.57
     hemor
    -0.57
     Tray
    -0.56
    atility
    -0.56
    POSITIVE LOGITS
    long
    0.96
    book
    0.90
    nings
    0.84
    ns
    0.75
    é¾įåĸļ士
    0.73
    lings
    0.73
    books
    0.72
    Reviewer
    0.72
    ning
    0.72
    INAL
    0.70
    Act Density 0.113%

    No Known Activations